Anomaly detection in MRI is of high clinical value in imaging and diagnosis. Unsupervised methods for anomaly detection provide interesting formulations based on reconstruction or latent embedding, offering a way to observe properties related to factorization. We study four existing modeling methods, and report our empirical observations using simple data science tools, to seek outcomes from the perspective of factorization as it would be most relevant to the task of unsupervised anomaly detection, considering the case of brain structural MRI. Our study indicates that anomaly detection algorithms that exhibit factorization related properties are well capacitated with delineatory capabilities to distinguish between normal and anomaly data. We have validated our observations in multiple anomaly and normal datasets.

新生儿重症监护病房（NICU）中的早产婴儿必须不断监测其心脏健康。常规的监测方法是基于接触的，使新生儿容易受到各种医院感染。基于视频的监视方法为非接触式测量开辟了潜在的途径。这项工作提供了一条管道，用于远程对NICU设置视频的心肺信号进行远程估算。我们提出了一个端到端深度学习（DL）模型，该模型集成了一种基于基于学习的方法来生成替代地面真理（SGT）标签以进行监督，从而避免了直接依赖对真实地面真相标签的依赖。我们进行了扩展的定性和定量分析，以检查我们提出的基于DL的管道的功效，并在估计的心率中达到了总平均平均绝对误差为4.6 BEATS（BPM）（BPM）和均方根均方根误差为6.2 bpm。

深度学习网络在快速磁共振成像（MRI）重建中显示出令人鼓舞的结果。在我们的工作中，我们开发了深层网络，以进一步提高重建的定量和感知质量。首先，我们提出了Reconsynergynet（RSN），该网络结合了在图像和傅立叶域上独立运行的互补益处。对于单线采集，我们引入了深层级联RSN（DC-RSN），这是一个与数据保真度（DF）单位交织在一起的RSN块的级联。其次，我们通过协助T1加权成像（T1WI）的帮助，这是T2加权成像（T2WI）的DC-RSN的结构恢复，这是一个短时间采集时间的序列。通过日志功能（高尔夫）融合的梯度为DC-RSN提供T1援助。此外，我们建议感知改进网络（PRN）来完善重建以获得更好的视觉信息保真度（VIF），这是一种与放射科医生对图像质量高度相关的指标。最后，对于多线圈采集，我们提出了可变拆分RSN（VS-RSN），深层块，每个块，包含RSN，多圈DF单元和加权平均模块。我们广泛验证了单线和多线圈采集的模型DC-RSN和VS-RSN，并报告最先进的性能。我们在FastMRI中获得了0.768、0.923、0.878的SSIM，单线圈-4X，多螺旋-4X和多型圈-8X的SSIM为0.878。我们还进行了实验，以证明基于高尔夫的T1援助和PRN的功效。

基于卷积神经网络的MR重建方法已经显示出提供快速和高质量的重建。具有基于CNN的模型的主要缺点是它缺乏灵活性，并且可以仅针对特定采集上下文限制实际适用性有效运行。通过获取上下文，我们的意思是三个输入设置的特定组合，即所认为的三种输入，在研究中的解剖学，欠采样掩模图案和欠采样的加速度。该模型可以在组合多个上下文的图像上共同培训。然而，该模型不符合上下文特定模型的性能，也不符合在火车时间内看不见的上下文。这需要在生成上下文特定权重时修改现有体系结构，以便将灵活性合并到多个上下文。我们提出了一个多次采集的上下文基础网络，称为MAC-Recordnet，用于MRI重建，灵活地到多个获取上下文，并更广泛地概括为在实际方案中适用性的未操作性上下文。所提出的网络具有MRI重建模块和动态重量预测（DWP）模块。 DWP模块将相应的获取上下文信息作为输入，并学习重建模块的上下文专用权重，在运行时使用上下文动态变化。我们表明，所提出的方法可以根据心脏和大脑数据集，高斯和笛卡尔欠采样模式和五个加速因子处理多个上下文。所提出的网络优于Naive联合训练的模型，并通过定量和定性地具有与上下文专用模型具有竞争力的结果。我们还通过在火车时间看不见的背景下测试了我们模型的普遍性。

Modern deep learning models are over-parameterized, where the optimization setup strongly affects the generalization performance. A key element of reliable optimization for these systems is the modification of the loss function. Sharpness-Aware Minimization (SAM) modifies the underlying loss function to guide descent methods towards flatter minima, which arguably have better generalization abilities. In this paper, we focus on a variant of SAM known as mSAM, which, during training, averages the updates generated by adversarial perturbations across several disjoint shards of a mini-batch. Recent work suggests that mSAM can outperform SAM in terms of test accuracy. However, a comprehensive empirical study of mSAM is missing from the literature -- previous results have mostly been limited to specific architectures and datasets. To that end, this paper presents a thorough empirical evaluation of mSAM on various tasks and datasets. We provide a flexible implementation of mSAM and compare the generalization performance of mSAM to the performance of SAM and vanilla training on different image classification and natural language processing tasks. We also conduct careful experiments to understand the computational cost of training with mSAM, its sensitivity to hyperparameters and its correlation with the flatness of the loss landscape. Our analysis reveals that mSAM yields superior generalization performance and flatter minima, compared to SAM, across a wide range of tasks without significantly increasing computational costs.

Recently developed methods for video analysis, especially models for pose estimation and behavior classification, are transforming behavioral quantification to be more precise, scalable, and reproducible in fields such as neuroscience and ethology. These tools overcome long-standing limitations of manual scoring of video frames and traditional "center of mass" tracking algorithms to enable video analysis at scale. The expansion of open-source tools for video acquisition and analysis has led to new experimental approaches to understand behavior. Here, we review currently available open-source tools for video analysis and discuss how to set up these methods for labs new to video recording. We also discuss best practices for developing and using video analysis methods, including community-wide standards and critical needs for the open sharing of datasets and code, more widespread comparisons of video analysis methods, and better documentation for these methods especially for new users. We encourage broader adoption and continued development of these tools, which have tremendous potential for accelerating scientific progress in understanding the brain and behavior.

我们考虑涉及大量突出点的突出指向的应用程序。通过理论和实证分析，我们开发了一种引导的直觉，以表明，当这些实例遵循某些结构时，大多数投影都位于多粒子的顶点上。为了有效地进行这些预测，我们推出了一个面向顶点的增量算法，将点投影到任何任意多托，以及给出特定算法，以迎合单位投影，并通过平面切割单位盒的多台零件。这种设置在Web级应用中特别有用，例如最佳匹配或分配问题。互联网市场（电子商务，乘车共享，食品交付，专业服务，广告等）中的几个问题可以配制为线性程序（LP），其中多种子约束需要整体优化过程中的投影步骤。我们表明，在最近的工作中，多体化投影是最昂贵的步骤，我们有效的投影算法有助于获得性能的大量改进。

In speech recognition, it is essential to model the phonetic content of the input signal while discarding irrelevant factors such as speaker variations and noise, which is challenging in low-resource settings. Self-supervised pre-training has been proposed as a way to improve both supervised and unsupervised speech recognition, including frame-level feature representations and Acoustic Word Embeddings (AWE) for variable-length segments. However, self-supervised models alone cannot learn perfect separation of the linguistic content as they are trained to optimize indirect objectives. In this work, we experiment with different pre-trained self-supervised features as input to AWE models and show that they work best within a supervised framework. Models trained on English can be transferred to other languages with no adaptation and outperform self-supervised models trained solely on the target languages.

Cybercriminals are moving towards zero-day attacks affecting resource-constrained devices such as single-board computers (SBC). Assuming that perfect security is unrealistic, Moving Target Defense (MTD) is a promising approach to mitigate attacks by dynamically altering target attack surfaces. Still, selecting suitable MTD techniques for zero-day attacks is an open challenge. Reinforcement Learning (RL) could be an effective approach to optimize the MTD selection through trial and error, but the literature fails when i) evaluating the performance of RL and MTD solutions in real-world scenarios, ii) studying whether behavioral fingerprinting is suitable for representing SBC's states, and iii) calculating the consumption of resources in SBC. To improve these limitations, the work at hand proposes an online RL-based framework to learn the correct MTD mechanisms mitigating heterogeneous zero-day attacks in SBC. The framework considers behavioral fingerprinting to represent SBCs' states and RL to learn MTD techniques that mitigate each malicious state. It has been deployed on a real IoT crowdsensing scenario with a Raspberry Pi acting as a spectrum sensor. More in detail, the Raspberry Pi has been infected with different samples of command and control malware, rootkits, and ransomware to later select between four existing MTD techniques. A set of experiments demonstrated the suitability of the framework to learn proper MTD techniques mitigating all attacks (except a harmfulness rootkit) while consuming <1 MB of storage and utilizing <55% CPU and <80% RAM.

Automated cellular instance segmentation is a process utilized for accelerating biological research for the past two decades, and recent advancements have produced higher quality results with less effort from the biologist. Most current endeavors focus on completely cutting the researcher out of the picture by generating highly generalized models. However, these models invariably fail when faced with novel data, distributed differently than the ones used for training. Rather than approaching the problem with methods that presume the availability of large amounts of target data and computing power for retraining, in this work we address the even greater challenge of designing an approach that requires minimal amounts of new annotated data as well as training time. We do so by designing specialized contrastive losses that leverage the few annotated samples very efficiently. A large set of results show that 3 to 5 annotations lead to models with accuracy that: 1) significantly mitigate the covariate shift effects; 2) matches or surpasses other adaptation methods; 3) even approaches methods that have been fully retrained on the target distribution. The adaptation training is only a few minutes, paving a path towards a balance between model performance, computing requirements and expert-level annotation needs.